Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3759 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.4658. Min Act: -0.0000

Data Index: 983689 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.2323. Min Act: -0.0000

Data Index: 1577850 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.9794. Min Act: -0.0000

Data Index: 199314 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.9839. Min Act: -0.0000

Data Index: 1482046 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.9693. Min Act: -0.0000

Data Index: 1534315 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.8168. Min Act: -0.0000

Data Index: 87843 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.8229. Min Act: -0.0000

Data Index: 425132 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.8104. Min Act: -0.0000

Data Index: 1461835 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1299265 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7259. Min Act: -0.0000

Data Index: 1450571 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7010. Min Act: -0.0000

Data Index: 1622664 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6823. Min Act: -0.0000

Data Index: 1526359 (Python Code)

Max Activating Token Index: 839

Text #12

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7264. Min Act: -0.0000

Data Index: 1472241 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6225. Min Act: -0.0000

Data Index: 20621 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6021. Min Act: -0.0000

Data Index: 1601732 (Python Code)

Max Activating Token Index: 981

Text #15

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5962. Min Act: -0.0000

Data Index: 38174 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1630181 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1521494 (Python Code)

Max Activating Token Index: 569

Text #18

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6463. Min Act: -0.0000

Data Index: 931444 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1563737 (Python Code)

Max Activating Token Index: 837